diff --git a/GPy/core/transformations.py b/GPy/core/transformations.py
index f7e59ab6..fcbfb548 100644
--- a/GPy/core/transformations.py
+++ b/GPy/core/transformations.py
@@ -39,8 +39,8 @@ class logexp(transformation):
         return '(+ve)'
 
 class logexp_clipped(transformation):
-    max_bound = 1e300
-    min_bound = 1e-10
+    max_bound = 1e250
+    min_bound = 1e-9
     log_max_bound = np.log(max_bound)
     log_min_bound = np.log(min_bound)
     def __init__(self, lower=1e-6):
@@ -49,11 +49,13 @@ class logexp_clipped(transformation):
     def f(self, x):
         exp = np.exp(np.clip(x, self.log_min_bound, self.log_max_bound))
         f = np.log(1. + exp)
+        if np.isnan(f).any():
+            import ipdb;ipdb.set_trace()
         return f
     def finv(self, f):
         return np.log(np.exp(np.clip(f, self.min_bound, self.max_bound)) - 1.)
     def gradfactor(self, f):
-        ef = np.exp(f)
+        ef = np.exp(f) # np.clip(f, self.min_bound, self.max_bound))
         gf = (ef - 1.) / ef
         return np.where(f < self.lower, 0, gf)
     def initialize(self, f):
diff --git a/GPy/examples/dimensionality_reduction.py b/GPy/examples/dimensionality_reduction.py
index 18995c50..4f713c1f 100644
--- a/GPy/examples/dimensionality_reduction.py
+++ b/GPy/examples/dimensionality_reduction.py
@@ -273,8 +273,8 @@ def bgplvm_simulation(optimize='scg',
         pylab.figure(); pylab.axis(); m.kern.plot_ARD()
     return m
 
-def mrd_simulation(plot_sim=False):
-    D1, D2, D3, N, M, Q = 150, 250, 300, 700, 3, 7
+def mrd_simulation(optimize=True, plot_sim=False):
+    D1, D2, D3, N, M, Q = 150, 250, 30, 300, 3, 7
     slist, Slist, Ylist = _simulate_sincos(D1, D2, D3, N, M, Q, plot_sim)
 
     from GPy.models import mrd
@@ -292,6 +292,13 @@ def mrd_simulation(plot_sim=False):
     m.constrain('variance|noise', logexp_clipped())
     m.ensure_default_constraints()
 
+    # DEBUG
+    np.seterr("raise")
+
+    if optimize:
+        print "Optimizing Model:"
+        m.optimize('scg', messages=1, max_iters=3e3)
+
     return m
 
 def brendan_faces():
diff --git a/GPy/inference/SCG.py b/GPy/inference/SCG.py
index e6ef25c0..f190d002 100644
--- a/GPy/inference/SCG.py
+++ b/GPy/inference/SCG.py
@@ -85,8 +85,6 @@ def SCG(f, gradf, x, optargs=(), maxiters=500, max_f_eval=500, display=True, xto
         # Increase effective curvature and evaluate step size alpha.
         delta = theta + beta * kappa
         if delta <= 0:
-            if display:
-                print ""
             delta = beta * kappa
             beta = beta - theta / kappa
 
diff --git a/GPy/models/Bayesian_GPLVM.py b/GPy/models/Bayesian_GPLVM.py
index 5511a1b9..464d7425 100644
--- a/GPy/models/Bayesian_GPLVM.py
+++ b/GPy/models/Bayesian_GPLVM.py
@@ -171,9 +171,6 @@ class Bayesian_GPLVM(sparse_GP, GPLVM):
         self.dbound_dZtheta = sparse_GP._log_likelihood_gradients(self)
         return np.hstack((self.dbound_dmuS.flatten(), self.dbound_dZtheta))
 
-    def _log_likelihood_normal_gradients(self):
-        Si, _, _, _ = pdinv(self.X_variance)
-
     def plot_latent(self, which_indices=None, *args, **kwargs):
 
         if which_indices is None: